Distributed multinomial regression

DOI10.48550/ARXIV.1311.6139zbMATH Open1454.62036arXiv1311.6139MaRDI QIDQ112152FDOQ112152

Authors: Matt Taddy, Matthew A. Taddy 

Publication date: 24 November 2013

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Abstract: This article introduces a model-based approach to distributed computing for multinomial logistic (softmax) regression. We treat counts for each response category as independent Poisson regressions via plug-in estimates for fixed effects shared across categories. The work is driven by the high-dimensional-response multinomial models that are used in analysis of a large number of random counts. Our motivating applications are in text analysis, where documents are tokenized and the token counts are modeled as arising from a multinomial dependent upon document attributes. We estimate such models for a publicly available data set of reviews from Yelp, with text regressed onto a large set of explanatory variables (user, business, and rating information). The fitted models serve as a basis for exploring the connection between words and variables of interest, for reducing dimension into supervised factor scores, and for prediction. We argue that the approach herein provides an attractive option for social scientists and other text analysts who wish to bring familiar regression tools to bear on text data.

Full work available at URL: https://arxiv.org/abs/1311.6139

Recommendations

• Variable selection in general multinomial logit models
• The negative multinomial logit model
• Distributed Bayesian machine learning procedures
• Optimal subsampling for softmax regression
• scientific article; zbMATH DE number 795293

zbMATH Keywords

Lassologistic regressioncomputational social sciencedistributed computingmultinomial inverse regressiontext analysis

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Generalized linear models (logistic models) (62J12)

Cites Work

• Statistical Analysis of Financial Data in S-Plus
• Regression and time series model selection in small samples
• Title not available (Why is that?)
• On the poisson approximation to the multinomial distribution
• The Poisson Approximation to the Poisson Binomial Distribution
• Title not available (Why is that?)
• Fisher lecture: Dimension reduction in regression
• Title not available (Why is that?)
• Multinomial Inverse Regression for Text Analysis

Cited In (17)

• Title not available (Why is that?)
• Time-dependent Poisson reduced rank models for political text data analysis
• Topic-adjusted visibility metric for scientific articles
• Distributed prediction from vertically partitioned data
• A Discussion of “Text Selection”
• Discussion of “Text Selection” by Bryan Kelly, Asaf Manela, and Alan Moreira
• Discussion on “Text Selection”
• Text Selection
• Distributional anchor regression
• Distributed Censored Regression Over Networks
• textir
• distrom
• Distributed adaptive Huber regression
• Multiclass-penalized logistic regression
• Graph-Assisted Inverse Regression for Count Data and Its Application to Sequencing Data
• Title not available (Why is that?)
• ADMM-softmax: an ADMM approach for multinomial logistic regression

This page was built for publication: Distributed multinomial regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q112152)